Two-party split learning is a popular technique for learning a model across feature-partitioned data. In this work, we explore whether it is possible for one party to steal the private label information from the other party during split training, and whether there are methods that can protect against such attacks. Specifically, we first formulate a realistic threat model and propose a privacy loss metric to quantify label leakage in split learning. We then show that there exist two simple yet effective methods within the threat model that can allow one party to accurately recover private ground-truth labels owned by the other party. To combat these attacks, we propose several random perturbation techniques, including $\texttt{Marvell}$, an approach that strategically finds the structure of the noise perturbation by minimizing the amount of label leakage (measured through our quantification metric) of a worst-case adversary. We empirically demonstrate the effectiveness of our protection techniques against the identified attacks, and show that $\texttt{Marvell}$ in particular has improved privacy-utility tradeoffs relative to baseline approaches.

翻译：双方分解学习是一种广受欢迎的方法,用来学习跨特性数据的模式。 在这项工作中,我们探讨一方能否在分解训练中偷取对方的私人标签信息,以及是否有方法可以防止这种攻击。具体地说,我们首先制定现实的威胁模式,提出隐私损失指标,以量化分解学习中的标签渗漏。然后,我们表明在威胁模式中存在两种简单而有效的方法,使一方能够准确收回对方拥有的私人地面真实标签。为了打击这些攻击,我们提议了几种随机扰动技术,包括美元(textt{Marvelll}$),这一方法从战略上找到噪音扰动的结构,将最坏的对手的标签渗漏量(通过我们的量化指标衡量)减少到最低限度。我们从经验上证明了我们保护技术对所查明的攻击的有效性,并表明美元(textt{Marvelil}特别是美元)改善了基线方法的私隐利交易。